Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913668734648320 |
|---|---|
| author | Acharya, Manish Zhang, Yifan Leach, Kevin Huang, Yu |
| author_facet | Acharya, Manish Zhang, Yifan Leach, Kevin Huang, Yu |
| contents | Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth program analysis. This study introduces AUTOPATCH, an in-context learning approach designed to bridge this gap by enabling LLMs to automatically generate optimized code. Inspired by how programmers learn and apply knowledge to optimize software, AUTOPATCH incorporates three key components: (1) an analogy-driven framework to align LLM optimization with human cognitive processes, (2) a unified approach that integrates historical code examples and CFG analysis for context-aware learning, and (3) an automated pipeline for generating optimized code through in-context prompting. Experimental results demonstrate that AUTOPATCH achieves a 7.3% improvement in execution efficiency over GPT-4o across common generated executable code, highlighting its potential to advance automated program runtime optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16692 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation Acharya, Manish Zhang, Yifan Leach, Kevin Huang, Yu Software Engineering Artificial Intelligence Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth program analysis. This study introduces AUTOPATCH, an in-context learning approach designed to bridge this gap by enabling LLMs to automatically generate optimized code. Inspired by how programmers learn and apply knowledge to optimize software, AUTOPATCH incorporates three key components: (1) an analogy-driven framework to align LLM optimization with human cognitive processes, (2) a unified approach that integrates historical code examples and CFG analysis for context-aware learning, and (3) an automated pipeline for generating optimized code through in-context prompting. Experimental results demonstrate that AUTOPATCH achieves a 7.3% improvement in execution efficiency over GPT-4o across common generated executable code, highlighting its potential to advance automated program runtime optimization. |
| title | Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2501.16692 |